Skip to content

Benchmark

SWE-bench Verified (Agentic Coding)

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

71.5%
Mean
77.2%
Median
5.7%
Std dev
65.8%
10th percentile
77.2%
90th percentile
65.8%
Min
65.8%77.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Sonnet 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.2%
2Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.8%

Data credits: Data by LLM Stats